Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury
Neurocritical Care · 2025-04 · 42 (2) · 387-397
DOI: 10.1007/s12028-024-02119-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurocritical Care, online erschienen am 25.09.2024. Verfasst von Peter Galos und 7 weiteren Autor:innen. Beteiligte Einrichtung: Division of Neurosurgery, Department of Medical Sciences, Uppsala University, Uppsala, Sweden. peter.galos@neuro.uu.se. Hauptthemen laut MEDLINE: Brain Injuries, Traumatic, Machine Learning, Intracranial Hypertension, Critical Care. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Vetenskapsrådet, Swedish government and Uppsala county council,, Kjell och Märta Beijers Stiftelse.
Abstract (Originalsprache)
Background
In neurointensive care, increased intracranial pressure (ICP) is a feared secondary brain insult in traumatic brain injury (TBI). A system that predicts ICP insults before they emerge may facilitate early optimization of the physiology, which may in turn lead to stopping the predicted ICP insult from occurring. The aim of this study was to evaluate the performance of different artificial intelligence models in predicting the risk of ICP insults.
Methods
The models were trained to predict risk of ICP insults starting within 30 min, using the Uppsala high frequency TBI dataset. A restricted dataset consisting of only monitoring data were used, and an unrestricted dataset using monitoring data as well as clinical data, demographic data, and radiological evaluations was used. Four different model classes were compared: Gaussian process regression, logistic regression, random forest classifier, and Extreme Gradient Boosted decision trees (XGBoost).
Results
Six hundred and two patients with TBI were included (total monitoring 138,411 h). On the task of predicting upcoming ICP insults, the Gaussian process regression model performed similarly on the Uppsala high frequency TBI dataset (sensitivity 93.2%, specificity 93.9%, area under the receiver operating characteristic curve [AUROC] 98.3%), as in earlier smaller studies. Using a more flexible model (XGBoost) resulted in a comparable performance (sensitivity 93.8%, specificity 94.6%, AUROC 98.7%). Adding more clinical variables and features further improved the performance of the models slightly (XGBoost: sensitivity 94.1%, specificity of 94.6%, AUROC 98.8%).
Conclusions
Artificial intelligence models have potential to become valuable tools for predicting ICP insults in advance during neurointensive care. The fact that common off-the-shelf models, such as XGBoost, performed well in predicting ICP insults opens new possibilities that can lead to faster advances in the field and earlier clinical implementations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Division of Neurosurgery, Department of Medical Sciences, Uppsala University, Uppsala, Sweden. peter.galos@neuro.uu.se.
- Division of Systems and Control, Department of Information Technology, Uppsala University, Uppsala, Sweden.
- Division of Neurosurgery, Department of Medical Sciences, Uppsala University, Uppsala, Sweden.
ORCID-Profile: Peter Galos
Förderung
- Vetenskapsrådet
- Swedish government and Uppsala county council,
- Kjell och Märta Beijers Stiftelse
- Uppsala University
Zitieren
APA
Galos, P., Hult, L., Zachariah, D., Lewén, A., Hånell, A., Howells, T., Schön, T. B., & Enblad, P. (2025). Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury. Neurocritical Care, 42(2), 387-397. https://doi.org/10.1007/s12028-024-02119-7
Vancouver
Galos P, Hult L, Zachariah D, Lewén A, Hånell A, Howells T, et al. Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury. Neurocritical Care. 2025;42(2):387-397. doi:10.1007/s12028-024-02119-7
BibTeX
@article{Galos2025,
author = {Galos, Peter and Hult, Ludvig and Zachariah, Dave and Lewén, Anders and Hånell, Anders and Howells, Timothy and Schön, Thomas B and Enblad, Per},
title = {Machine Learning Based Prediction of Imminent ICP Insults During Neurocritical Care of Traumatic Brain Injury},
journal = {Neurocritical Care},
year = {2025},
volume = {42},
number = {2},
pages = {387--397},
doi = {10.1007/s12028-024-02119-7}
}
EUVIMED